初始化项目，由ModelHub XC社区提供模型
Model: openSUSE/CVE-Backport-Qwen2.5-Coder-32B Source: Original Platform
This commit is contained in:
ModelHub XC
41
.gitattributes
vendored
Normal file
41
.gitattributes
vendored
Normal file
@@ -0,0 +1,41 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
cve-backport-codegen-v4-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
v4-lora-adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
cve-backport-codegen-v3-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
v3-lora-adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
cve-backport-codegen-v5-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
v5-lora-adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
16
Modelfile
Normal file
16
Modelfile
Normal file
@@ -0,0 +1,16 @@
|
||||
FROM cve-backport-codegen-v4-q8_0.gguf
|
||||
|
||||
PARAMETER temperature 0
|
||||
PARAMETER num_ctx 8192
|
||||
PARAMETER stop "<|im_end|>"
|
||||
PARAMETER stop "<|endoftext|>"
|
||||
|
||||
SYSTEM """You are a security patch backporting assistant.
|
||||
|
||||
Given vulnerable source code and a description of the upstream fix, output the FIXED version of the code.
|
||||
|
||||
Rules:
|
||||
- Output ONLY the fixed code, nothing else — no explanations, no markdown fences
|
||||
- Preserve exact formatting, indentation, and style of the original
|
||||
- Make ONLY the changes described in the fix — do not modify anything else
|
||||
- Do not add comments about what you changed"""
|
||||
180
README.md
Normal file
180
README.md
Normal file
@@ -0,0 +1,180 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen2.5-Coder-32B-Instruct
|
||||
tags:
|
||||
- security
|
||||
- patch-backporting
|
||||
- code-generation
|
||||
- qwen2
|
||||
- qlora
|
||||
- opensuse
|
||||
datasets:
|
||||
- openSUSE/cve-backport-codegen-dataset
|
||||
language:
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# CVE Backport Code Generation — Qwen2.5-Coder-32B (v5)
|
||||
|
||||
Fine-tuned [Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct) for security patch backporting via per-hunk code generation. Maintained as part of the openSUSE security tooling effort, alongside the [cve-backport-tool](https://github.com/openSUSE/cve-backport-tool) CLI.
|
||||
|
||||
Instead of generating unified diffs, this model takes a vulnerable code region and a fix description, and outputs the **fixed version of the code**. A programmatic diff then produces the final patch.
|
||||
|
||||
> **MoE variant available:** An MoE-based alternative built on
|
||||
> Qwen3-Coder-30B-A3B (3B active parameters) is hosted at
|
||||
> [anicka/cve-backport-codegen-v5-qwen3-coder-30b-a3b](https://huggingface.co/anicka/cve-backport-codegen-v5-qwen3-coder-30b-a3b).
|
||||
> It scores 91.9% recall on the same 100-example eval — 1.2 pt below this
|
||||
> dense model — while running roughly 10× faster at inference due to sparse
|
||||
> MoE activation. Recommended for bulk CVE backport workflows where
|
||||
> throughput matters.
|
||||
|
||||
## Quick Start
|
||||
|
||||
```bash
|
||||
git clone https://github.com/openSUSE/cve-backport-tool
|
||||
cd cve-backport-tool
|
||||
./setup.sh # downloads GGUF, registers with ollama
|
||||
|
||||
python3 cve-backport.py \
|
||||
--cve CVE-2024-1234 \
|
||||
--package curl \
|
||||
--patch upstream-fix.patch \
|
||||
--obs-fetch --obs-project openSUSE:Leap:15.6:Update \
|
||||
--retry 3
|
||||
```
|
||||
|
||||
## GGUF Downloads
|
||||
|
||||
| File | Quant | Size | Notes |
|
||||
|------|-------|------|-------|
|
||||
| `cve-backport-codegen-v5-q8_0.gguf` | Q8_0 | 33 GB | **Recommended** (v5, 93.1% recall, 94.4% precision, codegen-only) |
|
||||
| `cve-backport-codegen-v4-q8_0.gguf` | Q8_0 | 33 GB | v4, 93% recall, 95% precision (includes test generation training) |
|
||||
| `cve-backport-codegen-v3-q8_0.gguf` | Q8_0 | 33 GB | v3, 94% recall, 98% precision (legacy, smaller eval set) |
|
||||
|
||||
## Evaluation (v5)
|
||||
|
||||
Per-hunk evaluation on 100 held-out examples the model never saw during training:
|
||||
|
||||
| Metric | v5 | v4 | v3 (n=20) |
|
||||
|--------|:--:|:--:|:---------:|
|
||||
| Average recall | **93.1%** | 93% | 94% |
|
||||
| Average precision | **94.4%** | 95% | 98% |
|
||||
| Exact match | **83/100** | 87/100 | 16/20 |
|
||||
| Failures (<10%) | **3/100** | 4/100 | 0/20 |
|
||||
|
||||
By tier:
|
||||
- **Identical** (upstream patch applies directly): 93.7% recall (77/85 perfect)
|
||||
- **Adapted** (line numbers/context differ): 90.0% recall (13/15 perfect)
|
||||
|
||||
Adapted-tier recall has steadily improved: 71% (v1) → 86% (v4) → **90% (v5)**.
|
||||
|
||||
### What changed in v5
|
||||
|
||||
v5 uses a codegen-only dataset — all 36,166 training examples follow the same 3-turn format. v4 mixed in 772 five-turn test-generation examples which diluted codegen focus. Dropping those and training for 2 epochs (vs 1 in v4) improved adapted-tier recall.
|
||||
|
||||
### Comparison with Frontier Models
|
||||
|
||||
Same eval, same 100 examples, optimized prompts with markdown stripping:
|
||||
|
||||
| Model | Recall | Precision | Exact | Failures |
|
||||
|-------|--------|-----------|-------|----------|
|
||||
| **CVE Backport v5** (32B fine-tuned) | **93%** | **94%** | **83/100** | **3** |
|
||||
| Gemini 3.1 Pro (frontier, zero-shot) | 27% | 24% | 10/100 | 50 |
|
||||
| Gemini 2.0 Flash (frontier, zero-shot) | 13% | 17% | 4/100 | 81 |
|
||||
|
||||
Fine-tuning on 36K domain-specific examples outperforms frontier models by 3-7x on this task.
|
||||
|
||||
## Prompt Format
|
||||
|
||||
ChatML format. Each prompt covers one hunk region with 15 lines of context padding.
|
||||
|
||||
### Code Generation (3-turn)
|
||||
|
||||
**System:**
|
||||
```
|
||||
You are a security patch backporting assistant.
|
||||
|
||||
Given vulnerable source code and a description of the upstream fix, output the FIXED version of the code.
|
||||
|
||||
Rules:
|
||||
- Output ONLY the fixed code, nothing else — no explanations, no markdown fences
|
||||
- Preserve exact formatting, indentation, and style of the original
|
||||
- Make ONLY the changes described in the fix — do not modify anything else
|
||||
- Do not add comments about what you changed
|
||||
```
|
||||
|
||||
**User:**
|
||||
```
|
||||
## File: crypto/bn/bn.h
|
||||
## Lines: 280-310
|
||||
|
||||
\```c
|
||||
/* vulnerable source code region with 15 lines of context */
|
||||
\```
|
||||
|
||||
## Fix
|
||||
Add bounds check for BN_num_bits to prevent buffer over-read (CVE-2024-XXXX).
|
||||
```
|
||||
|
||||
**Assistant:** The fixed version of the code region (just the code, no markup).
|
||||
|
||||
## Training
|
||||
|
||||
| | |
|
||||
|---|---|
|
||||
| Base model | Qwen2.5-Coder-32B-Instruct |
|
||||
| Method | QLoRA (4-bit NF4, bf16 compute, double quantization) |
|
||||
| LoRA rank / alpha | 64 / 128 |
|
||||
| Epochs | 2 (8,228 steps) |
|
||||
| Training data | 36,166 train / 1,834 eval (codegen-only, all 3-turn) |
|
||||
| Effective batch size | 8 |
|
||||
| Learning rate | 1e-4 (cosine, 5% warmup) |
|
||||
| Max sequence length | 4,096 tokens |
|
||||
| Hardware | 2× NVIDIA H100 NVL 94GB |
|
||||
| Training time | 46.1 hours |
|
||||
| Final eval loss | 0.00602 |
|
||||
|
||||
## Reproduction via Teapot
|
||||
|
||||
This model is reproducible via the [teapot](https://github.com/anicka-net/teapot) training pipeline. Once the dataset is composed, training is a four-command sequence:
|
||||
|
||||
```bash
|
||||
git clone https://github.com/anicka-net/teapot
|
||||
cd teapot
|
||||
pip install -e .
|
||||
|
||||
# 1. Compose training data from the cve-backport module
|
||||
teapot compose configs/cve-backport.config \
|
||||
--output train-cve-backport.jsonl
|
||||
|
||||
# 2. Generate the QLoRA-HF launch script
|
||||
teapot train configs/cve-backport.config \
|
||||
--backend qlora-hf \
|
||||
--train-data train-cve-backport.jsonl \
|
||||
--eval-data eval-cve-backport.jsonl \
|
||||
--output train-cve-backport.sh
|
||||
|
||||
# 3. Train (2× H100 NVL 94GB; ~46 hours)
|
||||
bash train-cve-backport.sh
|
||||
|
||||
# 4. Final adapter is at output-teapot-cve-backport/final/
|
||||
```
|
||||
|
||||
The teapot config (`configs/cve-backport.config`) pins all the hyperparameters listed in the Training table above. The `qlora-hf` backend invokes `teapot.train_qlora_hf`, a thin wrapper over the HuggingFace `Trainer` with bitsandbytes 4-bit quantization and PEFT LoRA.
|
||||
|
||||
## LoRA Adapter and MoE Variant
|
||||
|
||||
The LoRA adapter for this model is hosted at [anicka/cve-backport-codegen-v5-qwen25-32b](https://huggingface.co/anicka/cve-backport-codegen-v5-qwen25-32b) for use with PEFT/transformers.
|
||||
|
||||
An MoE variant trained on the same dataset is available at [anicka/cve-backport-codegen-v5-qwen3-coder-30b-a3b](https://huggingface.co/anicka/cve-backport-codegen-v5-qwen3-coder-30b-a3b) — built on Qwen3-Coder-30B-A3B (3B active params), 91.9% recall on the same n=100 eval, ~10× faster inference.
|
||||
|
||||
## Known Issues
|
||||
|
||||
- The 3 failure cases (0% recall) are all complex libvirt patches involving multi-function adaptations across large files with significant structural differences. These likely require an agentic approach with source tree context.
|
||||
- Very long hunks (>2000 tokens) may be truncated due to the 4096-token training context.
|
||||
- Always review generated patches before applying to production systems.
|
||||
|
||||
## License
|
||||
|
||||
Apache-2.0 (inherited from Qwen2.5-Coder-32B-Instruct).
|
||||
3
cve-backport-codegen-v3-q8_0.gguf
Normal file
3
cve-backport-codegen-v3-q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9014851eea8f9de084526f2bb5435c058a752ffbd5d34a3849791e5a702b4fde
|
||||
size 34820884640
|
||||
3
cve-backport-codegen-v4-q8_0.gguf
Normal file
3
cve-backport-codegen-v4-q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ba2eae883112670577b81d22b43681775affb11391e3eeb17b5a92fcbe761cd3
|
||||
size 34820884640
|
||||
3
cve-backport-codegen-v5-q8_0.gguf
Normal file
3
cve-backport-codegen-v5-q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c652e608e4d7c4602ee39218d601cb76f2dcb6845fe1c92e9f715a8f3dacd4d8
|
||||
size 34820884672
|
||||
729
eval/recall-v4-n100.json
Normal file
729
eval/recall-v4-n100.json
Normal file
@@ -0,0 +1,729 @@
|
||||
{
|
||||
"module": "domain/cve-backport",
|
||||
"eval_type": "standard",
|
||||
"timestamp": "2026-03-28T09:42:46Z",
|
||||
"n_examples": 100,
|
||||
"metrics": {
|
||||
"avg_recall": 0.931,
|
||||
"avg_precision": 0.9463,
|
||||
"exact_match": 87,
|
||||
"perfect_count": 89,
|
||||
"failure_count": 4,
|
||||
"zero_failures": false
|
||||
},
|
||||
"per_tier": {
|
||||
"adapted": {
|
||||
"avg_recall": 0.8562,
|
||||
"count": 15,
|
||||
"perfect": 12
|
||||
},
|
||||
"identical": {
|
||||
"avg_recall": 0.9442,
|
||||
"count": 85,
|
||||
"perfect": 77
|
||||
}
|
||||
},
|
||||
"pass": false,
|
||||
"per_example": [
|
||||
{
|
||||
"id": "codegen-openssl-4598-0001-s_server-Use-2048-bit-DH--apps_s_server.c",
|
||||
"tier": "adapted",
|
||||
"recall": 0.36,
|
||||
"precision": 0.20689655172413793,
|
||||
"exact_match": false
|
||||
},
|
||||
{
|
||||
"id": "codegen-openssl-4769-openssl-CVE-2016-0797.patch-crypto_bn_bn.h",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-jasper-14141-jasper-CVE-2018-18873.patch-src_libjasper_ras_ras_enc.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-python-libxml2-python-12846-libxml2-python3-unicode-errors.patch-python_libxml.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-GraphicsMagick-13054-GraphicsMagick-dcm.c-update.patch-coders_dcm.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-libvirt-13730-f3ef7daf-xenconfig-e820-host.patch-src_libxl_xen_common.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-libvirt-13730-ae9e6c2a-qemu-allow-cond-format-probe.patch-src_util_virstoragefile.c",
|
||||
"tier": "identical",
|
||||
"recall": 0.725,
|
||||
"precision": 0.7631578947368421,
|
||||
"exact_match": false
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-10645-sysconf-uio-maxiov.patch-sysdeps_unix_sysv_linux_Makefile",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-tiff-9924-tiff-CVE-2019-7663.patch-tools_tiffcp.c",
|
||||
"tier": "identical",
|
||||
"recall": 0.8888888888888888,
|
||||
"precision": 0.8888888888888888,
|
||||
"exact_match": false
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-17211-sysconf-uio-maxiov.patch-sysdeps_unix_sysv_linux_Makefile",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-bluez-10285-0006-btmon-fix-multiple-segfaults.patch-monitor_packet.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": false
|
||||
},
|
||||
{
|
||||
"id": "codegen-bluez-11572-hcidump-Fix-memory-leak-with-malformed-packet.patch-tools_hcidump.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-python-base-17077-python-skip_random_failing_tests.patch-Lib_test_test_multiprocessing.py",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-python-base-10735-python-bsddb6.diff-Modules__bsddb.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-10645-mman-map-sync.patch-sysdeps_unix_sysv_linux_sh_bits_mman.h",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-17211-syslog-locking.patch-misc_syslog.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-17211-i386-memmove-sse2-unaligned.patch-string_test-memmove.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-10645-remove-nss-nis-compat.patch-nss_grp-lookup.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-python-17077-reproducible.patch-Lib_py_compile.py",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-libvirt-13730-967f4eeb-xenconfig-event-channels.patch-src_libxl_xen_xl.c",
|
||||
"tier": "identical",
|
||||
"recall": 0.19047619047619047,
|
||||
"precision": 0.36363636363636365,
|
||||
"exact_match": false
|
||||
},
|
||||
{
|
||||
"id": "codegen-python-10735-python-2.7.5-multilib.patch-Makefile.pre.in",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-GraphicsMagick-13054-GraphicsMagick-CVE-2019-19951.patch-coders_miff.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-libvirt-13730-b7d6648d-conf-add-e820-host.patch-docs_formatdomain.html.in",
|
||||
"tier": "identical",
|
||||
"recall": 0.0,
|
||||
"precision": 0.0,
|
||||
"exact_match": false
|
||||
},
|
||||
{
|
||||
"id": "codegen-libvirt-13730-libvirt-suse-netcontrol.patch-configure.ac",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-10645-i386-memmove-sse2-unaligned.patch-sysdeps_i386_i686_multiarch_memcpy-sse2-unaligned.S",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-17211-euc-kr-overrun.patch-iconvdata_Makefile",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-17211-glibc-2.3.90-langpackdir.diff-intl_loadmsgcat.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-libvirt-13730-libxl-set-migration-constraints.patch-docs_manpages_virsh.rst",
|
||||
"tier": "identical",
|
||||
"recall": 0.0,
|
||||
"precision": 0.0,
|
||||
"exact_match": false
|
||||
},
|
||||
{
|
||||
"id": "codegen-libvirt-13730-0001-Extract-stats-functions-from-the-qemu-driver.patch-src_qemu_qemu_driver.c",
|
||||
"tier": "identical",
|
||||
"recall": 0.0,
|
||||
"precision": 0.0,
|
||||
"exact_match": false
|
||||
},
|
||||
{
|
||||
"id": "codegen-python-base-10735-python-2.7.5-multilib.patch-Lib_trace.py",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-python-doc-10735-python-bsddb6.diff-Lib_bsddb_test_test_all.py",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-python-doc-10735-python-bsddb6.diff-Modules_bsddb.h",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-python-10735-python-bsddb6.diff-Modules__bsddb.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-python-doc-10735-python-2.7.5-multilib.patch-Lib_site.py",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-python-doc-10735-python-skip_random_failing_tests.patch-Lib_test_test_subprocess.py",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-openssl-4769-openssl-CVE-2014-3566.patch-apps_s_client.c",
|
||||
"tier": "adapted",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-openssl-4769-0001-libcrypto-Hide-library-pr-crypto_des_des_locl.h",
|
||||
"tier": "adapted",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-openssl-4769-0001-libcrypto-Hide-library-pr-crypto_modes_modes_lcl.h",
|
||||
"tier": "adapted",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-openssl-4769-0001-libcrypto-Hide-library-pr-crypto_modes_gcm128.c",
|
||||
"tier": "adapted",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-openssl-4769-openssl-CVE-2014-8275.patch-crypto_asn1_a_type.c",
|
||||
"tier": "adapted",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-17211-0003-S390-Unify-31-64bit-memcpy.patch-sysdeps_s390_s390-64_multiarch_Makefile",
|
||||
"tier": "adapted",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-17211-iconv-option-parsing.patch-iconv_gconv_int.h",
|
||||
"tier": "adapted",
|
||||
"recall": 0.03333333333333333,
|
||||
"precision": 0.5,
|
||||
"exact_match": false
|
||||
},
|
||||
{
|
||||
"id": "codegen-ghostscript-mini-5761-fix-mutex-crash.patch-base_gp_psync.c",
|
||||
"tier": "adapted",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-GraphicsMagick-9414-GraphicsMagick-CVE-2014-9845.patch-coders_dib.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-ImageMagick-9270-ImageMagick-CVE-2016-7540.patch-coders_rgf.c",
|
||||
"tier": "adapted",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-ImageMagick-9270-ImageMagick-CVE-2017-14989.patch-magick_annotate.c",
|
||||
"tier": "adapted",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-GraphicsMagick-9192-GraphicsMagick-CVE-2018-16645.patch-coders_dib.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-ImageMagick-9059-ImageMagick-CVE-2016-6491.patch-magick_property.c",
|
||||
"tier": "adapted",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-ImageMagick-9059-ImageMagick-CVE-2017-14175.patch-coders_xbm.c",
|
||||
"tier": "adapted",
|
||||
"recall": 0.45,
|
||||
"precision": 0.9473684210526315,
|
||||
"exact_match": false
|
||||
},
|
||||
{
|
||||
"id": "codegen-openssh-8445-openssh-7.2p2-X_forward_with_disabled_ipv6.patch-openssh-7.2p2_channels.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-openssh-8445-openssh-7.2p2-disable_short_DH_parameters.patch-openssh-7.2p2_readconf.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-openssh-8445-openssh-7.2p2-prevent_private_key_leakage.patch-openssh-7.2p2_sshbuf.h",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-apache2-8062-apache2-CVE-2016-8740.patch-modules_http2_h2_session.c",
|
||||
"tier": "adapted",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-LibVNCServer-7946-LibVNCServer-CVE-2014-6052.patch-libvncclient_rfbproto.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-testsuite-7805-0004-S390-Fix-handling-of-DXC-byte-in-FPC-register.patch-sysdeps_s390_fpu_fesetenv.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-testsuite-7805-0013-S390-Optimize-stpcpy-and-wcpcpy.patch-string_test-stpcpy.c",
|
||||
"tier": "identical",
|
||||
"recall": 0.9615384615384616,
|
||||
"precision": 0.9615384615384616,
|
||||
"exact_match": false
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-testsuite-7805-0016-S390-Optimize-strcat-and-wcscat.patch-sysdeps_s390_multiarch_strcat.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-testsuite-7805-0021-S390-Optimize-strchrnul-and-wcschrnul.patch-string_test-strchr.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-testsuite-7805-0027-S390-Optimize-memccpy.patch-string_memccpy.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-testsuite-7805-avx512-knl-memcpy.patch-sysdeps_x86_64_multiarch_mempcpy.S",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-testsuite-7805-errorcheck-mutex-no-elision.patch-nptl_pthread_mutex_timedlock.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-testsuite-7805-glob-altdirfunc.patch-manual_pattern.texi",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-testsuite-7805-iconv-reset-input-buffer.patch-iconv_gconv_simple.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-testsuite-7805-malloc-Fix-list_lock-arena-lock-deadlock-BZ-19182.patch-malloc_arena.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-testsuite-7805-nis-initgroups-status.patch-nis_nss_nis_nis-initgroups.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-testsuite-7805-powerpc-elision-adapt-param.patch-sysdeps_unix_sysv_linux_powerpc_elision-lock.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-testsuite-7805-prelink-elf-rtype-class.patch-elf_dl-lookup.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-testsuite-7805-reduce-edns-payload.patch-resolv_res_query.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-testsuite-7805-s390-runtime-resolve.patch-sysdeps_s390_bits_link.h",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-testsuite-7805-send-dg-buffer-overflow.patch-resolv_res_send.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-testsuite-7805-strftime-range-check.patch-time_tst-strftime.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-utils-7805-0004-S390-Fix-handling-of-DXC-byte-in-FPC-register.patch-sysdeps_s390_fpu_fsetexcptflg.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-utils-7805-0013-S390-Optimize-stpcpy-and-wcpcpy.patch-wcsmbs_wcpcpy.c",
|
||||
"tier": "identical",
|
||||
"recall": 0.8,
|
||||
"precision": 1.0,
|
||||
"exact_match": false
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-utils-7805-0017-S390-Optimize-strncat-wcsncat.patch-benchtests_bench-strncat.c",
|
||||
"tier": "identical",
|
||||
"recall": 0.6888888888888889,
|
||||
"precision": 1.0,
|
||||
"exact_match": false
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-utils-7805-0023-S390-Optimize-strspn-and-wcsspn.patch-benchtests_bench-strspn.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-utils-7805-0028-S390-Optimize-wmemset.patch-sysdeps_s390_multiarch_wmemset.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-utils-7805-catopen-unbound-alloca.patch-catgets_catgets.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-utils-7805-fnmatch-collating-elements.patch-posix_fnmatch_loop.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-utils-7805-glob-altdirfunc.patch-posix_glob.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-utils-7805-iconv-reset-input-buffer.patch-iconv_gconv_simple.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-utils-7805-malloc-Prevent-arena-free_list-from-turning-cyclic-B.patch-malloc_malloc.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-utils-7805-nscd-gc-crash.patch-nscd_grpcache.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-utils-7805-powerpc-elision-enable-envvar.patch-sysdeps_unix_sysv_linux_powerpc_elision-conf.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-utils-7805-prelink-elf-rtype-class.patch-elf_dl-lookup.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-utils-7805-reduce-edns-payload.patch-resolv_res_query.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-utils-7805-s390-runtime-resolve.patch-sysdeps_s390_bits_link.h",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-utils-7805-send-dg-buffer-overflow.patch-resolv_res_send.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-utils-7805-sunrpc-xdr-memory.patch-sunrpc_xdr.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-7805-0004-S390-Fix-handling-of-DXC-byte-in-FPC-register.patch-sysdeps_s390_fpu_ftestexcept.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-7805-errorcheck-mutex-no-elision.patch-nptl_pthread_mutex_timedlock.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-7805-nis-initgroups-status.patch-nis_nss_nis_nis-initgroups.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-7805-powerpc-tabort-usage.patch-sysdeps_unix_sysv_linux_powerpc_syscall.S",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-glibc-7805-tzset-tzname.patch-timezone_Makefile",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-curl-7678-curl-CVE-2014-3620.patch-tests_data_test61",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-curl-7678-curl-CVE-2015-3153.patch-tests_data_test1527",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-curl-7678-curl-CVE-2016-8623.patch-lib_cookie.h",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-openvpn-7411-0001-Fix-remote-triggerable-memory-leaks-CVE-2017-7521.patch-src_openvpn_ssl_verify_openssl.c",
|
||||
"tier": "adapted",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-openvpn-7411-openvpn-2.3.x-fixed-multiple-low-severity-issues.patch-src_openvpn_error.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-GraphicsMagick-7399-GraphicsMagick-CVE-2014-9845.patch-coders_dib.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
},
|
||||
{
|
||||
"id": "codegen-GraphicsMagick-7342-GraphicsMagick-CVE-2016-7101.patch-coders_sgi.c",
|
||||
"tier": "identical",
|
||||
"recall": 1.0,
|
||||
"precision": 1.0,
|
||||
"exact_match": true
|
||||
}
|
||||
]
|
||||
}
|
||||
666
eval/test-generation-v4-n50.json
Normal file
666
eval/test-generation-v4-n50.json
Normal file
@@ -0,0 +1,666 @@
|
||||
{
|
||||
"module": "domain/cve-backport",
|
||||
"eval_type": "test-generation",
|
||||
"timestamp": "2026-03-28T10:06:38Z",
|
||||
"n_examples": 50,
|
||||
"metrics": {
|
||||
"avg_score": 0.6661,
|
||||
"median_score": 0.802,
|
||||
"good_tests": 50,
|
||||
"errors": 0,
|
||||
"zero_errors": true
|
||||
},
|
||||
"pass": true,
|
||||
"per_example": [
|
||||
{
|
||||
"id": "example_0",
|
||||
"cve": "CVE-2020-27749",
|
||||
"package": "grub2",
|
||||
"tier": "identical",
|
||||
"score": 0.485,
|
||||
"ref_overlap": 0.321,
|
||||
"prompt_overlap": 0.122,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 14
|
||||
},
|
||||
{
|
||||
"id": "example_14",
|
||||
"cve": "CVE-2020-1752",
|
||||
"package": "glibc",
|
||||
"tier": "identical",
|
||||
"score": 0.455,
|
||||
"ref_overlap": 0.286,
|
||||
"prompt_overlap": 0.062,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 9
|
||||
},
|
||||
{
|
||||
"id": "example_28",
|
||||
"cve": "CVE-2019-9674",
|
||||
"package": "python",
|
||||
"tier": "identical",
|
||||
"score": 0.367,
|
||||
"ref_overlap": 0.091,
|
||||
"prompt_overlap": 0.106,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 7
|
||||
},
|
||||
{
|
||||
"id": "example_42",
|
||||
"cve": "CVE-2019-1551",
|
||||
"package": "openssl-1_1",
|
||||
"tier": "identical",
|
||||
"score": 0.75,
|
||||
"ref_overlap": 0.857,
|
||||
"prompt_overlap": 0.109,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 11
|
||||
},
|
||||
{
|
||||
"id": "example_56",
|
||||
"cve": "CVE-2020-10029",
|
||||
"package": "glibc",
|
||||
"tier": "identical",
|
||||
"score": 0.358,
|
||||
"ref_overlap": 0.111,
|
||||
"prompt_overlap": 0.01,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 4
|
||||
},
|
||||
{
|
||||
"id": "example_70",
|
||||
"cve": "CVE-2024-53907",
|
||||
"package": "python-Django",
|
||||
"tier": "identical",
|
||||
"score": 0.822,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.109,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 21
|
||||
},
|
||||
{
|
||||
"id": "example_84",
|
||||
"cve": "CVE-2019-3885",
|
||||
"package": "pacemaker",
|
||||
"tier": "identical",
|
||||
"score": 0.328,
|
||||
"ref_overlap": 0.05,
|
||||
"prompt_overlap": 0.014,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 5
|
||||
},
|
||||
{
|
||||
"id": "example_98",
|
||||
"cve": "CVE-2021-3933",
|
||||
"package": "openexr",
|
||||
"tier": "identical",
|
||||
"score": 0.397,
|
||||
"ref_overlap": 0.188,
|
||||
"prompt_overlap": 0.014,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_112",
|
||||
"cve": "CVE-2020-8286",
|
||||
"package": "curl",
|
||||
"tier": "identical",
|
||||
"score": 0.671,
|
||||
"ref_overlap": 0.727,
|
||||
"prompt_overlap": 0.039,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 11
|
||||
},
|
||||
{
|
||||
"id": "example_126",
|
||||
"cve": "CVE-2021-22924",
|
||||
"package": "curl",
|
||||
"tier": "identical",
|
||||
"score": 0.507,
|
||||
"ref_overlap": 0.4,
|
||||
"prompt_overlap": 0.037,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 10
|
||||
},
|
||||
{
|
||||
"id": "example_140",
|
||||
"cve": "CVE-2019-7397",
|
||||
"package": "GraphicsMagick",
|
||||
"tier": "identical",
|
||||
"score": 0.455,
|
||||
"ref_overlap": 0.3,
|
||||
"prompt_overlap": 0.025,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_154",
|
||||
"cve": "CVE-2018-0495",
|
||||
"package": "libgcrypt",
|
||||
"tier": "identical",
|
||||
"score": 0.363,
|
||||
"ref_overlap": 0.12,
|
||||
"prompt_overlap": 0.015,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_168",
|
||||
"cve": "CVE-2017-12133",
|
||||
"package": "glibc",
|
||||
"tier": "identical",
|
||||
"score": 0.712,
|
||||
"ref_overlap": 0.778,
|
||||
"prompt_overlap": 0.114,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 10
|
||||
},
|
||||
{
|
||||
"id": "example_182",
|
||||
"cve": "CVE-2017-6441",
|
||||
"package": "php7",
|
||||
"tier": "identical",
|
||||
"score": 0.554,
|
||||
"ref_overlap": 0.5,
|
||||
"prompt_overlap": 0.021,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 4
|
||||
},
|
||||
{
|
||||
"id": "example_196",
|
||||
"cve": "CVE-2015-8994",
|
||||
"package": "php7",
|
||||
"tier": "identical",
|
||||
"score": 0.804,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.018,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 4
|
||||
},
|
||||
{
|
||||
"id": "example_210",
|
||||
"cve": "CVE-2016-8866",
|
||||
"package": "GraphicsMagick",
|
||||
"tier": "identical",
|
||||
"score": 0.472,
|
||||
"ref_overlap": 0.333,
|
||||
"prompt_overlap": 0.024,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_224",
|
||||
"cve": "CVE-2018-19541",
|
||||
"package": "jasper",
|
||||
"tier": "synthetic-adapted",
|
||||
"score": 0.517,
|
||||
"ref_overlap": 0.429,
|
||||
"prompt_overlap": 0.014,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_238",
|
||||
"cve": "CVE-2019-9636",
|
||||
"package": "python3-base",
|
||||
"tier": "synthetic-adapted",
|
||||
"score": 0.806,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.03,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 4
|
||||
},
|
||||
{
|
||||
"id": "example_252",
|
||||
"cve": "CVE-2017-15597",
|
||||
"package": "xen",
|
||||
"tier": "synthetic-adapted",
|
||||
"score": 0.368,
|
||||
"ref_overlap": 0.133,
|
||||
"prompt_overlap": 0.008,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 4
|
||||
},
|
||||
{
|
||||
"id": "example_266",
|
||||
"cve": "CVE-2018-0735",
|
||||
"package": "openssl-1_1",
|
||||
"tier": "adapted",
|
||||
"score": 0.805,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.023,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_280",
|
||||
"cve": "CVE-2021-27219",
|
||||
"package": "glib2",
|
||||
"tier": "identical",
|
||||
"score": 0.803,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.015,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_294",
|
||||
"cve": "CVE-2018-5711",
|
||||
"package": "gd",
|
||||
"tier": "identical",
|
||||
"score": 0.803,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.016,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_308",
|
||||
"cve": "CVE-2019-11041",
|
||||
"package": "php7",
|
||||
"tier": "synthetic-adapted",
|
||||
"score": 0.803,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.014,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 4
|
||||
},
|
||||
{
|
||||
"id": "example_322",
|
||||
"cve": "CVE-2022-0113",
|
||||
"package": "chromium",
|
||||
"tier": "synthetic-adapted",
|
||||
"score": 0.802,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.009,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_336",
|
||||
"cve": "CVE-2019-17498",
|
||||
"package": "libssh2_org",
|
||||
"tier": "identical",
|
||||
"score": 0.804,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.019,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_350",
|
||||
"cve": "CVE-2019-5868",
|
||||
"package": "chromium",
|
||||
"tier": "identical",
|
||||
"score": 0.803,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.016,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_364",
|
||||
"cve": "CVE-2018-17456",
|
||||
"package": "git",
|
||||
"tier": "identical",
|
||||
"score": 0.604,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.021,
|
||||
"structural": 0.333,
|
||||
"has_assert": false,
|
||||
"has_function": false,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_378",
|
||||
"cve": "CVE-2017-3737",
|
||||
"package": "openssl",
|
||||
"tier": "identical",
|
||||
"score": 0.736,
|
||||
"ref_overlap": 0.818,
|
||||
"prompt_overlap": 0.136,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 13
|
||||
},
|
||||
{
|
||||
"id": "example_392",
|
||||
"cve": "CVE-2021-3500",
|
||||
"package": "djvulibre",
|
||||
"tier": "synthetic-adapted",
|
||||
"score": 0.806,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.029,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_406",
|
||||
"cve": "CVE-2019-12838",
|
||||
"package": "slurm",
|
||||
"tier": "synthetic-adapted",
|
||||
"score": 0.803,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.016,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_420",
|
||||
"cve": "CVE-2016-9042",
|
||||
"package": "ntp",
|
||||
"tier": "synthetic-adapted",
|
||||
"score": 0.804,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.019,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_434",
|
||||
"cve": "CVE-2018-5732",
|
||||
"package": "dhcp",
|
||||
"tier": "synthetic-adapted",
|
||||
"score": 0.803,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.016,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_448",
|
||||
"cve": "CVE-2019-2614",
|
||||
"package": "mariadb",
|
||||
"tier": "identical",
|
||||
"score": 0.606,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.029,
|
||||
"structural": 0.333,
|
||||
"has_assert": false,
|
||||
"has_function": false,
|
||||
"lines": 4
|
||||
},
|
||||
{
|
||||
"id": "example_462",
|
||||
"cve": "CVE-2019-9947",
|
||||
"package": "python-base",
|
||||
"tier": "identical",
|
||||
"score": 0.805,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.026,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 4
|
||||
},
|
||||
{
|
||||
"id": "example_476",
|
||||
"cve": "CVE-2018-9135",
|
||||
"package": "ImageMagick",
|
||||
"tier": "adapted",
|
||||
"score": 0.803,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.017,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_490",
|
||||
"cve": "CVE-2017-9798",
|
||||
"package": "apache2",
|
||||
"tier": "adapted",
|
||||
"score": 0.803,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.013,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_504",
|
||||
"cve": "CVE-2016-9317",
|
||||
"package": "gd",
|
||||
"tier": "identical",
|
||||
"score": 0.805,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.027,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_518",
|
||||
"cve": "CVE-2018-20852",
|
||||
"package": "python-doc",
|
||||
"tier": "synthetic-adapted",
|
||||
"score": 0.806,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.031,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 4
|
||||
},
|
||||
{
|
||||
"id": "example_532",
|
||||
"cve": "CVE-2016-9603",
|
||||
"package": "xen",
|
||||
"tier": "synthetic-adapted",
|
||||
"score": 0.802,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.008,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 4
|
||||
},
|
||||
{
|
||||
"id": "example_546",
|
||||
"cve": "CVE-2020-9490",
|
||||
"package": "apache2",
|
||||
"tier": "synthetic-adapted",
|
||||
"score": 0.802,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.011,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_560",
|
||||
"cve": "CVE-2017-3144",
|
||||
"package": "dhcp",
|
||||
"tier": "synthetic-adapted",
|
||||
"score": 0.802,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.012,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_574",
|
||||
"cve": "CVE-2017-17479",
|
||||
"package": "openjpeg2",
|
||||
"tier": "synthetic-adapted",
|
||||
"score": 0.803,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.017,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_588",
|
||||
"cve": "CVE-2021-3781",
|
||||
"package": "ghostscript-mini",
|
||||
"tier": "identical",
|
||||
"score": 0.804,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.018,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_602",
|
||||
"cve": "CVE-2018-20103",
|
||||
"package": "haproxy",
|
||||
"tier": "identical",
|
||||
"score": 0.805,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.026,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_616",
|
||||
"cve": "CVE-2016-8862",
|
||||
"package": "ImageMagick",
|
||||
"tier": "identical",
|
||||
"score": 0.804,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.022,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_630",
|
||||
"cve": "CVE-2020-13977",
|
||||
"package": "nagios",
|
||||
"tier": "identical",
|
||||
"score": 0.809,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.043,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 3
|
||||
},
|
||||
{
|
||||
"id": "example_644",
|
||||
"cve": "CVE-2018-1060",
|
||||
"package": "python3",
|
||||
"tier": "synthetic-adapted",
|
||||
"score": 0.803,
|
||||
"ref_overlap": 1.0,
|
||||
"prompt_overlap": 0.017,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 4
|
||||
},
|
||||
{
|
||||
"id": "example_658",
|
||||
"cve": "CVE-2018-10931",
|
||||
"package": "cobbler",
|
||||
"tier": "synthetic-adapted",
|
||||
"score": 0.446,
|
||||
"ref_overlap": 0.25,
|
||||
"prompt_overlap": 0.105,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 10
|
||||
},
|
||||
{
|
||||
"id": "codegen-curl-10079-libcurl-ocloexec.patch-cookie.c",
|
||||
"cve": "CVE-2018-16839",
|
||||
"package": "curl",
|
||||
"tier": "identical",
|
||||
"score": 0.322,
|
||||
"ref_overlap": 0.0,
|
||||
"prompt_overlap": 0.111,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 9
|
||||
},
|
||||
{
|
||||
"id": "codegen-python3-11362-CVE-2019-16056-email-parse-addr.patch-Lib_email__header_value_parser.py",
|
||||
"cve": "CVE-2019-16056",
|
||||
"package": "python3",
|
||||
"tier": "identical",
|
||||
"score": 0.307,
|
||||
"ref_overlap": 0.0,
|
||||
"prompt_overlap": 0.036,
|
||||
"structural": 1.0,
|
||||
"has_assert": true,
|
||||
"has_function": true,
|
||||
"lines": 4
|
||||
}
|
||||
]
|
||||
}
|
||||
207
v3-lora-adapter/README.md
Normal file
207
v3-lora-adapter/README.md
Normal file
@@ -0,0 +1,207 @@
|
||||
---
|
||||
base_model: Qwen/Qwen2.5-Coder-32B-Instruct
|
||||
library_name: peft
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- base_model:adapter:Qwen/Qwen2.5-Coder-32B-Instruct
|
||||
- lora
|
||||
- transformers
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.18.1
|
||||
46
v3-lora-adapter/adapter_config.json
Normal file
46
v3-lora-adapter/adapter_config.json
Normal file
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"alora_invocation_tokens": null,
|
||||
"alpha_pattern": {},
|
||||
"arrow_config": null,
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "Qwen/Qwen2.5-Coder-32B-Instruct",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"ensure_weight_tying": false,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 128,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.05,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"peft_version": "0.18.1",
|
||||
"qalora_group_size": 16,
|
||||
"r": 64,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"gate_proj",
|
||||
"down_proj",
|
||||
"o_proj",
|
||||
"k_proj",
|
||||
"v_proj",
|
||||
"q_proj",
|
||||
"up_proj"
|
||||
],
|
||||
"target_parameters": null,
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_dora": false,
|
||||
"use_qalora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
3
v3-lora-adapter/adapter_model.safetensors
Normal file
3
v3-lora-adapter/adapter_model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0ba9f9c9096604ad1bd0850ac0ed4f80605faa0e1a6f1bf26c2694cd2722f0b1
|
||||
size 2147605960
|
||||
54
v3-lora-adapter/chat_template.jinja
Normal file
54
v3-lora-adapter/chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- message.content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
3
v3-lora-adapter/tokenizer.json
Normal file
3
v3-lora-adapter/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:21e2b58ce119ac9c0d306b7a35d538fe02f55e7f2af95cb0a2d563e892790684
|
||||
size 11421991
|
||||
29
v3-lora-adapter/tokenizer_config.json
Normal file
29
v3-lora-adapter/tokenizer_config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"is_local": false,
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
3
v3-lora-adapter/training_args.bin
Normal file
3
v3-lora-adapter/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2ac0894ba8ea16b0d31710d5bf4f88a4f0fb60d1b12ff714c04fd84dabd0349b
|
||||
size 5265
|
||||
207
v4-lora-adapter/README.md
Normal file
207
v4-lora-adapter/README.md
Normal file
@@ -0,0 +1,207 @@
|
||||
---
|
||||
base_model: Qwen/Qwen2.5-Coder-32B-Instruct
|
||||
library_name: peft
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- base_model:adapter:Qwen/Qwen2.5-Coder-32B-Instruct
|
||||
- lora
|
||||
- transformers
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.18.1
|
||||
46
v4-lora-adapter/adapter_config.json
Normal file
46
v4-lora-adapter/adapter_config.json
Normal file
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"alora_invocation_tokens": null,
|
||||
"alpha_pattern": {},
|
||||
"arrow_config": null,
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "Qwen/Qwen2.5-Coder-32B-Instruct",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"ensure_weight_tying": false,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 128,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.05,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"peft_version": "0.18.1",
|
||||
"qalora_group_size": 16,
|
||||
"r": 64,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"up_proj",
|
||||
"v_proj",
|
||||
"q_proj",
|
||||
"down_proj",
|
||||
"k_proj",
|
||||
"gate_proj",
|
||||
"o_proj"
|
||||
],
|
||||
"target_parameters": null,
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_dora": false,
|
||||
"use_qalora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
3
v4-lora-adapter/adapter_model.safetensors
Normal file
3
v4-lora-adapter/adapter_model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c233458f3600a3f6af3f76d8e78a624fddcb5711d1eb37a1509bb99174f6d30b
|
||||
size 2147605960
|
||||
54
v4-lora-adapter/chat_template.jinja
Normal file
54
v4-lora-adapter/chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- message.content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
3
v4-lora-adapter/tokenizer.json
Normal file
3
v4-lora-adapter/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:21e2b58ce119ac9c0d306b7a35d538fe02f55e7f2af95cb0a2d563e892790684
|
||||
size 11421991
|
||||
29
v4-lora-adapter/tokenizer_config.json
Normal file
29
v4-lora-adapter/tokenizer_config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"is_local": false,
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
3
v4-lora-adapter/training_args.bin
Normal file
3
v4-lora-adapter/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e6cfbd2c9ba8ecc68ac35524e39cd40d4708b8f997e39f325a94ca512d0ba264
|
||||
size 5265
|
||||
261
v5-lora-adapter/README.md
Normal file
261
v5-lora-adapter/README.md
Normal file
@@ -0,0 +1,261 @@
|
||||
---
|
||||
base_model: Qwen/Qwen2.5-Coder-32B-Instruct
|
||||
library_name: peft
|
||||
pipeline_tag: text-generation
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
tags:
|
||||
- security
|
||||
- cve
|
||||
- patches
|
||||
- backporting
|
||||
- opensuse
|
||||
- suse
|
||||
- linux
|
||||
- code-generation
|
||||
- lora
|
||||
- qlora
|
||||
- transformers
|
||||
datasets:
|
||||
- anicka/cve-backport-codegen-dataset
|
||||
model-index:
|
||||
- name: cve-backport-codegen-v5-qwen25-32b
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Security Patch Backporting
|
||||
dataset:
|
||||
type: anicka/cve-backport-codegen-dataset
|
||||
name: CVE Backport Codegen Dataset
|
||||
metrics:
|
||||
- name: Recall
|
||||
type: recall
|
||||
value: 0.931
|
||||
- name: Precision
|
||||
type: precision
|
||||
value: 0.944
|
||||
- name: Exact Match
|
||||
type: exact_match
|
||||
value: 0.83
|
||||
---
|
||||
|
||||
# CVE Backport Codegen v5 — Qwen2.5-Coder-32B QLoRA
|
||||
|
||||
Fine-tuned code generation model for backporting upstream CVE security fixes
|
||||
to older SUSE/openSUSE package versions. Given vulnerable source code and an
|
||||
upstream fix description, the model outputs the corrected code. A separate
|
||||
tool then diffs the output against the original to produce a patch.
|
||||
|
||||
This is a **per-hunk code generation** approach: the model sees one region of
|
||||
source code at a time and returns the fixed version, rather than generating
|
||||
raw unified diffs. This yields higher accuracy than patch-format models
|
||||
because the model works in its natural domain (code) rather than a
|
||||
meta-format (diffs).
|
||||
|
||||
## What's New in v5
|
||||
|
||||
v5 uses a unified **codegen-only dataset** — all 36,166 training examples
|
||||
follow the same 3-turn format (system / user with code + fix description /
|
||||
assistant with fixed code). v4 mixed in 5-turn test-generation examples;
|
||||
v5 drops those to focus entirely on codegen quality.
|
||||
|
||||
| Metric | v5 | v4 | v1 |
|
||||
|--------|:--:|:--:|:--:|
|
||||
| **Recall** | **93.1%** | 93% | 91% |
|
||||
| **Precision** | **94.4%** | 95% | — |
|
||||
| **Exact match** | **83/100** | 87/100 | — |
|
||||
| **Adapted recall** | **90.0%** | 86% | 71% |
|
||||
| **Identical recall** | 93.7% | 94% | 94% |
|
||||
|
||||
Adapted-tier recall has steadily improved: 71% (v1) → 86% (v4) → **90% (v5)**.
|
||||
The codegen-only dataset gives the model a cleaner training signal for the
|
||||
core task.
|
||||
|
||||
## Model Details
|
||||
|
||||
| | |
|
||||
|---|---|
|
||||
| **Base model** | [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct) |
|
||||
| **Method** | QLoRA (4-bit NF4, double quantization, bf16 compute) |
|
||||
| **LoRA rank / alpha** | 64 / 128 |
|
||||
| **LoRA dropout** | 0.05 |
|
||||
| **LoRA targets** | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
|
||||
| **Training data** | 36,166 train / 1,834 eval examples |
|
||||
| **Epochs** | 2 (8,228 steps) |
|
||||
| **Effective batch size** | 8 (1 × grad_accum 8) |
|
||||
| **Learning rate** | 1e-4 (cosine schedule, 5% warmup) |
|
||||
| **Max sequence length** | 4,096 tokens |
|
||||
| **Optimizer** | AdamW fused, weight decay 0.01 |
|
||||
| **Hardware** | 2× NVIDIA H100 NVL 94GB |
|
||||
| **Training time** | 46.1 hours |
|
||||
| **Train loss (avg)** | 0.0215 |
|
||||
| **Eval loss (final)** | 0.00602 |
|
||||
| **PEFT version** | 0.18.1 |
|
||||
|
||||
## Files
|
||||
|
||||
This repository contains:
|
||||
|
||||
- **LoRA adapter** (`adapter_model.safetensors`, `adapter_config.json`) — merge with the base model using PEFT
|
||||
- **GGUF Q8_0** (`cve-backport-codegen-v5-q8_0.gguf`, 33GB) — ready for llama.cpp / ollama
|
||||
|
||||
## Evaluation
|
||||
|
||||
Evaluated on 100 held-out examples (zero CVE overlap with training) using
|
||||
the Q8_0 GGUF served via llama-server (temperature=0, ctx=8192).
|
||||
|
||||
### Overall
|
||||
|
||||
| Metric | Value |
|
||||
|--------|-------|
|
||||
| Avg recall | 93.1% |
|
||||
| Avg precision | 94.4% |
|
||||
| Exact match | 83/100 |
|
||||
| Perfect (100% recall) | 90/100 |
|
||||
| Failures (0% recall) | 3/100 |
|
||||
|
||||
### By Tier
|
||||
|
||||
| Tier | Count | Avg Recall | Perfect |
|
||||
|------|:-----:|:----------:|:-------:|
|
||||
| **Identical** (upstream applies as-is) | 85 | 93.7% | 77/85 |
|
||||
| **Adapted** (requires modification) | 15 | 90.0% | 13/15 |
|
||||
|
||||
### Failure Analysis
|
||||
|
||||
The 3 zero-recall cases are all complex libvirt patches (multi-function
|
||||
adaptations across large files with significant structural differences
|
||||
between versions). These are known hard cases that likely require an
|
||||
agentic approach with source tree context.
|
||||
|
||||
## Training Data
|
||||
|
||||
The v5 dataset contains real SUSE/openSUSE maintenance patches paired
|
||||
with their upstream CVE fixes, converted to a per-hunk codegen format:
|
||||
|
||||
- **36,166 train + 1,834 eval** examples (strict CVE-level split, zero overlap)
|
||||
- All examples use a **3-turn ChatML format** (system / user / assistant)
|
||||
- Per-hunk extraction with 15-line context padding, nearby hunks merged
|
||||
- Covers C, C++, Python, shell, Java, JavaScript, Go, and more
|
||||
- Sources: openSUSE Build Service maintenance incidents
|
||||
|
||||
### Input Format
|
||||
|
||||
```
|
||||
## File: path/to/file.c
|
||||
## Lines: 100-130
|
||||
|
||||
```c
|
||||
/* 15 lines before the change */
|
||||
vulnerable_code_here();
|
||||
/* 15 lines after the change */
|
||||
```
|
||||
|
||||
## Fix
|
||||
Description of what the upstream patch changes in this region.
|
||||
```
|
||||
|
||||
### Output Format
|
||||
|
||||
The model outputs the fixed version of the code region (just the code,
|
||||
no diff headers or markup).
|
||||
|
||||
## Usage
|
||||
|
||||
### With llama.cpp / llama-server (GGUF)
|
||||
|
||||
```bash
|
||||
llama-server \
|
||||
--model cve-backport-codegen-v5-q8_0.gguf \
|
||||
--port 8403 \
|
||||
--n-gpu-layers 99 \
|
||||
--ctx-size 8192
|
||||
```
|
||||
|
||||
### With the CVE Backport Tool
|
||||
|
||||
The recommended way to use this model is via the
|
||||
[cve-backport-tool](https://github.com/anicka-net/cve-backport-tool),
|
||||
which handles patch parsing, source extraction, model inference, and
|
||||
diff generation:
|
||||
|
||||
```bash
|
||||
python3 cve-backport.py \
|
||||
--cve CVE-2024-1234 \
|
||||
--package openssl-1.1.1d \
|
||||
--patch upstream.patch \
|
||||
--source-dir /path/to/source/ \
|
||||
--backend openai \
|
||||
--retry 3
|
||||
```
|
||||
|
||||
### With transformers + PEFT (adapter)
|
||||
|
||||
```python
|
||||
from peft import PeftModel
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
base = AutoModelForCausalLM.from_pretrained(
|
||||
"Qwen/Qwen2.5-Coder-32B-Instruct",
|
||||
torch_dtype="bfloat16",
|
||||
device_map="auto",
|
||||
)
|
||||
model = PeftModel.from_pretrained(base, "anicka/cve-backport-codegen-v5-qwen25-32b")
|
||||
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-Coder-32B-Instruct")
|
||||
```
|
||||
|
||||
### Prompt Template (ChatML)
|
||||
|
||||
```
|
||||
<|im_start|>system
|
||||
You are a security patch backporting assistant.
|
||||
|
||||
Given vulnerable source code and a description of the upstream fix, output the FIXED version of the code.
|
||||
|
||||
Rules:
|
||||
- Output ONLY the fixed code, nothing else
|
||||
- Preserve all surrounding context exactly
|
||||
- Apply only the described fix
|
||||
<|im_end|>
|
||||
<|im_start|>user
|
||||
## File: crypto/bn/bn.h
|
||||
## Lines: 280-310
|
||||
|
||||
```c
|
||||
/* source code region */
|
||||
```
|
||||
|
||||
## Fix
|
||||
Add bounds check for BN_num_bits to prevent buffer over-read.
|
||||
<|im_end|>
|
||||
<|im_start|>assistant
|
||||
```
|
||||
|
||||
## Limitations
|
||||
|
||||
- **Best at identical-tier patches** (upstream fix applies directly) — 93.7% recall
|
||||
- **Good at adapted patches** (90% recall) but complex multi-function adaptations
|
||||
across structurally different versions remain challenging
|
||||
- **Context window**: 4,096 token training limit means very large functions or
|
||||
multi-file patches may be truncated
|
||||
- **No compilation feedback**: the model generates code in a single pass without
|
||||
verifying it compiles. Use `--retry` in the CLI tool for iterative correction.
|
||||
- Always review generated patches before applying to production systems
|
||||
|
||||
## Related
|
||||
|
||||
- **CLI tool**: [cve-backport-tool](https://github.com/anicka-net/cve-backport-tool)
|
||||
- **Dataset**: [anicka/cve-backport-codegen-dataset](https://huggingface.co/datasets/anicka/cve-backport-codegen-dataset)
|
||||
- **Previous version (v1)**: [anicka/cve-backport-codegen-qwen25-32b-v1](https://huggingface.co/anicka/cve-backport-codegen-qwen25-32b-v1)
|
||||
|
||||
## Citation
|
||||
|
||||
```bibtex
|
||||
@misc{cve-backport-codegen-v5,
|
||||
title={CVE Backport Codegen v5: Fine-tuned Qwen2.5-Coder-32B for Security Patch Backporting},
|
||||
author={Anna Maresova},
|
||||
year={2026},
|
||||
url={https://huggingface.co/anicka/cve-backport-codegen-v5-qwen25-32b}
|
||||
}
|
||||
```
|
||||
46
v5-lora-adapter/adapter_config.json
Normal file
46
v5-lora-adapter/adapter_config.json
Normal file
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"alora_invocation_tokens": null,
|
||||
"alpha_pattern": {},
|
||||
"arrow_config": null,
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "Qwen/Qwen2.5-Coder-32B-Instruct",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"ensure_weight_tying": false,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 128,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.05,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"peft_version": "0.18.1",
|
||||
"qalora_group_size": 16,
|
||||
"r": 64,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"gate_proj",
|
||||
"o_proj",
|
||||
"down_proj",
|
||||
"up_proj",
|
||||
"k_proj",
|
||||
"v_proj",
|
||||
"q_proj"
|
||||
],
|
||||
"target_parameters": null,
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_dora": false,
|
||||
"use_qalora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
3
v5-lora-adapter/adapter_model.safetensors
Normal file
3
v5-lora-adapter/adapter_model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:644bd0c861027440a38e5a6d59e4fc8e5629568a86a68881f735d68dd04b839c
|
||||
size 2147605960
|
||||
24
v5-lora-adapter/added_tokens.json
Normal file
24
v5-lora-adapter/added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
54
v5-lora-adapter/chat_template.jinja
Normal file
54
v5-lora-adapter/chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- message.content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
151388
v5-lora-adapter/merges.txt
Normal file
151388
v5-lora-adapter/merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
31
v5-lora-adapter/special_tokens_map.json
Normal file
31
v5-lora-adapter/special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
v5-lora-adapter/tokenizer.json
Normal file
3
v5-lora-adapter/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:83396048d512ec1f3178af0d7c1f79a226bba041822614b0e26a4fd2d4b55bf7
|
||||
size 11421995
|
||||
207
v5-lora-adapter/tokenizer_config.json
Normal file
207
v5-lora-adapter/tokenizer_config.json
Normal file
@@ -0,0 +1,207 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
3
v5-lora-adapter/training_args.bin
Normal file
3
v5-lora-adapter/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:18d5482439b903314c5777c6cb1050193782f8e89ed3d18122237dc3b827c686
|
||||
size 5905
|
||||
1
v5-lora-adapter/vocab.json
Normal file
1
v5-lora-adapter/vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user